core vs headlong
Self-hosted, always-on "personal AI OS": watches your apps, keeps a persistent memory graph, and acts autonomously within guardrails — a product, not a library for building agents. — versus — Persistent-agency agent harness in ~10K lines of Bash: it keeps thinking between messages, thinks by writing shell commands, and one shared mind serves a whole team over Slack or Telegram.
Same ambition — an always-on agent that carries your context and acts on its own. Core is a product with a memory graph and guardrails; Headlong is 10K lines of shell you are expected to read, fork and point at your own machine.
| core | headlong | |
|---|---|---|
| Stars | 2.0k | 1.0k |
| Forks | 189 | 95 |
| Language | TypeScript | Shell |
| License | NOASSERTION | Apache-2.0 |
| Last activity | 10 days ago | today |
| Topics | agents, memory | agents, memory |
| Curated connections | 11 | 6 |
core — the curator's take
Reach for CORE when you want an event-driven, self-hosted personal assistant that notices things on its own, remembers across sessions via a memory graph, and acts across your apps with per-action approval gates. NOT the pick if you want a framework to embed agents inside your own software (it's a product/OS, not a toolkit), nor if you need to run a multi-agent team/company with org charts and budgets — that's paperclip's lane.
headlong — the curator's take
Read this if you think harnesses have converged. Headlong drops the tool system entirely — the agent thinks by writing Bash, so `curl` is the HTTP client and `jq` the JSON parser — and it never stops: your message lands in an ongoing thought stream as one more observation, and the agent decides whether to answer. The trajectory is a fork/merge DAG of jsonl files, and context is a projection of it at exponentially decaying resolution, so nothing is compacted away in place. Laude Institute research alpha: it runs real shell commands around the clock at $1-2/hour, so use a spend-capped key and let the installer put it in Docker. Not the pick if you want a reactive, per-user, request/response coding agent — that mode exists but the whole design is aimed elsewhere.